DatBench: Discriminative, Faithful, and Efficient VLM Evaluations

• URL: http://arxiv.org/abs/2601.02316v2
• Date: Wed, 14 Jan 2026 06:10:23 GMT
• Title: DatBench: Discriminative, Faithful, and Efficient VLM Evaluations
• Authors: DatologyAI, :, Siddharth Joshi, Haoli Yin, Rishabh Adiga, Ricardo Monti, Aldo Carranza, Alex Fang, Alvin Deng, Amro Abbas, Brett Larsen, Cody Blakeney, Darren Teh, David Schwab, Fan Pan, Haakon Mongstad, Jack Urbanek, Jason Lee, Jason Telanoff, Josh Wills, Kaleigh Mentzer, Luke Merrick, Parth Doshi, Paul Burstein, Pratyush Maini, Scott Loftin, Spandan Das, Tony Jiang, Vineeth Dorna, Zhengping Wang, Bogdan Gaza, Ari Morcos, Matthew Leavitt,
• Abstract summary: Empirical evaluation serves as the primary compass guiding research progress in foundation models.<n>We propose three desiderata that evaluations should satisfy: faithfulness to the modality and application, discriminability between models of varying quality, and efficiency in compute.<n>We release DatBench-Full, a cleaned evaluation suite of 33 datasets spanning nine VLM capabilities, and DatBench, a discriminative subset that achieves 13x average speedup.
• Score: 17.234602646114997
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Empirical evaluation serves as the primary compass guiding research progress in foundation models. Despite a large body of work focused on training frontier vision-language models (VLMs), approaches to their evaluation remain nascent. To guide their maturation, we propose three desiderata that evaluations should satisfy: (1) faithfulness to the modality and application, (2) discriminability between models of varying quality, and (3) efficiency in compute. Through this lens, we identify critical failure modes that violate faithfulness and discriminability, misrepresenting model capabilities: (i) multiple-choice formats reward guessing, poorly reflect downstream use cases, and saturate early as models improve; (ii) blindly solvable questions, which can be answered without images, constitute up to 70% of some evaluations; and (iii) mislabeled or ambiguous samples compromise up to 42% of examples in certain datasets. Regarding efficiency, the computational burden of evaluating frontier models has become prohibitive: by some accounts, nearly 20% of development compute is devoted to evaluation alone. Rather than discarding existing benchmarks, we curate them via transformation and filtering to maximize fidelity and discriminability. We find that converting multiple-choice questions to generative tasks reveals sharp capability drops of up to 35%. In addition, filtering blindly solvable and mislabeled samples improves discriminative power while simultaneously reducing computational cost. We release DatBench-Full, a cleaned evaluation suite of 33 datasets spanning nine VLM capabilities, and DatBench, a discriminative subset that achieves 13x average speedup (up to 50x) while closely matching the discriminative power of the original datasets. Our work outlines a path toward evaluation practices that are both rigorous and sustainable as VLMs continue to scale.

Related papers

• Evaluating Self-Correcting Vision Agents Through Quantitative and Qualitative Metrics [0.0]
  Vision-Language Agents (VLAs) can decompose complex visual tasks into executable tool-based plans.<n>Recent benchmarks have begun to evaluate iterative self-correction, but its quantitative limits and dominant reasoning bottlenecks remain poorly characterized.
  arXiv  Detail & Related papers  (2026-01-14T15:17:11Z)
• Self-Improving VLM Judges Without Human Annotations [74.29324865147838]
  We present a framework to self-train a VLM judge model without any human preference annotations, using only self-synthesized data.<n>Our method improves a Llama-3.2-11B multimodal judge from 0.38 to 0.51 in overall accuracy on Multimodal RewardBench.<n>The overall strength of these human-annotation-free results suggest the potential for a future self-judge that evolves alongside rapidly improving VLM capabilities.
  arXiv  Detail & Related papers  (2025-12-02T20:52:19Z)
• Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study [91.78803511141975]
  This work focuses on the roles of positive and negative samples in scaling reinforcement learning.<n>We identify substantial data inefficiency in group relative policy optimization, where over half of the samples yield zero advantage.<n>We investigate unstable performance across various reasoning models and benchmarks, attributing instability to uncertain problems with ambiguous outcomes.
  arXiv  Detail & Related papers  (2025-06-05T11:47:10Z)
• Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs [7.197702136906138]
  We propose an uncertainty-aware fairness metric, UCerF, to enable a fine-grained evaluation of model fairness.<n> observing data size, diversity, and clarity issues in current datasets, we introduce a new gender-occupation fairness evaluation dataset.<n>We establish a benchmark, using our metric and dataset, and apply it to evaluate the behavior of ten open-source AI systems.
  arXiv  Detail & Related papers  (2025-05-29T20:45:18Z)
• VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks [49.0793012627959]
  We present VAPO, a novel framework tailored for reasoning models within the value-based paradigm.<n>VAPO attains a state-of-the-art score of $mathbf60.4$.<n>In direct comparison under identical experimental settings, VAPO outperforms the previously reported results of DeepSeek-R1-Zero-Qwen-32B and DAPO by more than 10 points.
  arXiv  Detail & Related papers  (2025-04-07T14:21:11Z)
• IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation [15.895295957106772]
  We propose an ID-induced prompt synthesis framework for evaluating Large Language Models (LLMs) Our data synthesis framework prioritizes both breadth and specificity. It can generate prompts that comprehensively evaluate the capabilities of LLMs. We will release a dataset of over 3,000 carefully crafted prompts to facilitate evaluation research of LLMs.
  arXiv  Detail & Related papers  (2024-09-27T16:29:12Z)
• Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving [55.93813178692077]
  We present RoboBEV, an extensive benchmark suite designed to evaluate the resilience of BEV algorithms.<n>We assess 33 state-of-the-art BEV-based perception models spanning tasks like detection, map segmentation, depth estimation, and occupancy prediction.<n>Our experimental results also underline the efficacy of strategies like pre-training and depth-free BEV transformations in enhancing robustness against out-of-distribution data.
  arXiv  Detail & Related papers  (2024-05-27T17:59:39Z)
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision [51.176061115977774]
  We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP) We then systematically evaluate existing methods for mitigating bias in these models with respect to our taxonomy. Specifically, we evaluate OpenAI's CLIP and OpenCLIP models for key applications, such as zero-shot classification, image retrieval and image captioning.
  arXiv  Detail & Related papers  (2023-10-18T10:32:39Z)
• Robust Outlier Rejection for 3D Registration with Variational Bayes [70.98659381852787]
  We develop a novel variational non-local network-based outlier rejection framework for robust alignment. We propose a voting-based inlier searching strategy to cluster the high-quality hypothetical inliers for transformation estimation.
  arXiv  Detail & Related papers  (2023-04-04T03:48:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.